Hire an AI art pipeline planner

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A budget sheet per asset type: triangles, texture sizes, LOD levels and draw calls
• Texture and compression rules for each platform
• A review routine for new assets, from first import to sign-off
• Limits for shaders and effects, with a check for mobile cost
• A profiling plan that says what to measure and in which tool

How it does the job well

• You cannot open an engine or run a profiler. Say Not run for any check you could not do. Never say a check passed when you did not run it.
• The profile's numbers (triangle counts, texture sizes, particle caps, compression formats) are examples from one project. Use them only as starting values and label each "starting value, check against your device". Prefer the user's own budgets and target hardware.
• Shader and script code is an untested sketch. Say so above every block. Do not claim it compiles.
• Engines differ. Say which engine a rule applies to. If the user names Unity, Unreal or Godot, point to the matching engine agent for engine-specific work.
• Do not invent a fact about the user's project. If a figure is not from the user, label it as an assumption.
• Start from the user's task and the content, then the layout. Decoration comes last.
• Design every state: empty, loading, error, long text and mobile.

Mistakes it avoids

• Approving an asset from a modelling-tool preview. Review it in the engine, under the game's lighting.
• Giving a hard number with no source and no label.
• Blaming artists. State the limit and the fix.
• Designing only the happy path at desktop width.
• Copying a reference's logo, text or claims instead of learning from its structure.
• Handing over a picture without the sizes, tokens and behaviour a developer needs.

What a good result looks like

An example, not your task: Art production is about to start and artists need clear limits.

• Asset budgets. Triangles, texture size, LOD levels and draw calls for each asset type.
• Texture rules. Compression and mipmap rules per platform and texture type.
• Effect and shader limits. Caps on particles and see-through layers, and a mobile-safe or PC-only flag for each shader.
• Asset review routine. The stages every asset passes before sign-off, with a pass rule for each.
• Profiling plan. What to measure, in which tool, where in the scene and against which budget.
• Sketches. Optional shader or check script drafts, marked untested.

How the work is checked

• Every screen has its states, breakpoints and interactions written down.
• Colour pairs and type sizes pass the stated contrast checks.
• The handoff names components, tokens and open questions.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Herb Lubalin and Massimo Vignelli would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Fix the limits. It confirms engine, platforms, frame rate target and weakest device. Gaps are asked once, then marked MISSING.
• Set the budgets. It writes triangle, texture, LOD and draw call budgets per asset type, each labelled as a starting value.
• Write the texture rules. It sets import, mipmap and compression rules per platform, and says to import at source size.
• Set shader and effect limits. It caps particles and see-through layers, asks for a mobile-safe shader or a PC-only flag, and lists what to check.
• Plan the review routine. Each asset passes import, lighting, LOD and a final profile check before sign-off.
• Plan the profiling. It lists what to measure, where in the scene and against which budget.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id technical-artist only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/technical-artist/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Your engine and the platforms you ship to, such as PC, console or mobile
• Your frame rate target and the weakest device you must support
• Your art style, and the asset types you need rules for, such as characters, props and effects
• A profiler screenshot or a description of a slow scene (optional)
• Budgets you already have (optional)

Helpful context (optional)

• A profiler capture or screenshot of your slowest scene
• A list of your current assets with triangle counts
• The device you test on, with its model name

Tools and access

• Claude, ChatGPT or Gemini: Any chat AI can write the sheets. Pick one that can read a profiler screenshot.

Functions and deliverables

• Art pipeline planner: Plan a game art pipeline with budgets for models, textures and effects, LOD and import rules, and a review routine, for any engine or platform.
  • A budget sheet per asset type: triangles, texture sizes, LOD levels and draw calls
  • Texture and compression rules for each platform
  • A review routine for new assets, from first import to sign-off
  • Limits for shaders and effects, with a check for mobile cost
  • A profiling plan that says what to measure and in which tool
  Source: Michael Sitarzewski and Agency Agents contributors.
• Image and video pipeline planner: Plan your image and video pipeline: formats, sizes, video hosting and a tidy asset library, so your site loads fast and stays organized.
  • A plan for image formats and sizes
  • A video hosting recommendation
  • A structure for your shared asset library
  • Upload steps for each person on your team
  • A list of changes to make, in order
  Source: RampStack.
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Herb Lubalin: Develop a wordmark, headline or poster through Herb Lubalin’s recorded approach. Make the letters carry one idea and check how well they read.
  • Your problem worked on the way Herb Lubalin would: their questions, their method, their push-back
  • The answer or the work, in Herb Lubalin's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Massimo Vignelli: Plan a layout or visual system using Massimo Vignelli’s recorded approach. Start with meaning, set clear rules and check what readers understand.
  • Your problem worked on the way Massimo Vignelli would: their questions, their method, their push-back
  • The answer or the work, in Massimo Vignelli's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• Art production is about to start and artists need clear limits.
• The game runs below its frame rate target and you do not know what to cut first.
• You work in more than one engine and want one set of art rules.
• A new effect or shader looks good, and you worry about its cost on mobile.

Limits to check before starting

• You use Unity and need a shader graph planned. Use the Unity Shader Graph artist.
• You use Unreal and need materials, Niagara or PCG planned. Use the Unreal technical artist.
• You use Godot and need a shader plan. Use the Godot Shader Developer agent.
• You want the art itself made. Hire an artist or use an image tool.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the pack and add it to your AI as a skill. If you cannot, paste SKILL.md, then references/source-agent.md, then your brief into a new chat. Claude, ChatGPT and Gemini all work.
• Paste your engine, platforms and frame rate target first. Then add the asset types you need rules for.
• Say "Write the budget sheet and review routine. Mark any number you cannot tie to my target hardware."
• Check each number against your slowest device. Change what does not fit before you share the sheet.
• Give the budget sheet to artists before they model. Use the review routine on the first few assets.
• Run your engine's profiler on a real scene. Paste the results back to review a slow scene.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/technical-artist for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.